The future of player data
Christofer Clemens, Head of DFB-Scouting and Match Analysis/Senior National Team at the Deutscher Fußball-Bund e.V., shares his experience with data at the bench at the FIFA Confederations Cup 2017
Do you see any benefits of having player/team stats available in the technical area in real time?
The use of real-time data in the technical area is a real benefit. Data adds another component to the relationship between the technical scouting and analysis department and the coaching team. The analysts are generally responsible for collecting, interpreting and applying the data while the coaching staff are the recipients of this information and make decisions directly affecting the team. Up until now, the processes for impacting the game were purely backed up by subjective observations – with all pros and cons. Reliable data now allows to validate these decision-making processes much more objectively. The common technical-tactical data is complemented with physical data and, more importantly, can be linked to footage from a number of different camera perspectives allowing the coaching staff to have a much better overview and to be able to more easily explain certain decisions to the players. The improved communication channel between the analysts and the technical zone means better decisions can be made during the match thereby changing its dynamic in a positive way. This however also represents a new challenge for coaching staff.
Another considerable factor is player load management. The first 3 or 4 games are potentially not as critical but exact player profiles can be established over time that can then be used as benchmarks for making decisions relating to the load a player is subjected to and can be used as a means to prevent injuries, not least with the growing demands towards the players in international football today.
Based on your expert knowledge, what is your vision for data in football and especially during matches?
In addition to the above aspects, the future of data analysis will, in my opinion, lie in the use of real-time positional data and in modelled machine learning during matches. Positional data – particularly taking the position of the ball into account – will provide us with all relevant constellations for the opponent and the ball in the context of the Laws of the Game. By using clear patterns, it is possible to calculate behaviour and potential solutions almost automatically. The dataset will always be the same for everyone involved, but it will be down to each individual team to use and interpret the dataset and draw its own conclusions. This means that the competitive advantage in using this data will primarily lie in how the coaching staff is able to apply to the team’s own tactics and game plan. Fast neuronal networks or pattern recognition on the basis of pre-defined parameters will help to discover clear tactical instructions and above all formulate them in a way so that they can also be conveyed to players in an easy-to understand way. Above all, however, it could allow to close the gap between “what happened” and “what could have happened, if...”. For this application the underlying technology for making sense of the data will be as important as the data itself. The beauty of it all is, however, that it will still exclusively be down to the players on the pitch to find the best solutions in constantly changing conditions. All of this could however make it easier for them.
What can football learn from other sports using data for the improvement of the game?
Football simply cannot afford to close itself off from technological developments in general and in particular those used in other sports, and, as has been proven by the use of the video assistant referee (VAR) system or by the pilot project for data transmission in the technical area, it is not doing so. Other sports such as field hockey or American football are maybe a step ahead of us and have already gained experience in these areas – experience that football now will and has to gain – which, in my opinion, will then render some reservations irrelevant. Generally speaking, the objective of using technology and data in sport should not be to make the game more predictable or more clinical. This would affect any sport, and ultimately make it less appealing. It is rather about being able to more fairly assess crucial situations in light of increasingly complex physical and cognitive conditions as well as technically better trained players and, above all, about improving player performances both in terms of technical-tactical development and controlling their workload. The correct data, when used with the correct technology and when interpreted correctly, can have a major impact, and ultimately help improve the quality of the game.
The maxim of any sport is for the best team to win, which is obviously a noble but not always achievable objective. The use of reliable data provides another opportunity – when used correctly – to get closer to this goal and, furthermore, to provide clearer justifications and more objective standards for the evaluation of a player’s impact or a team’s ability.